基于忆阻器的近似计算方法  

Approximate computing method based on memristors

作　　者：季宇 张悠慧[1] 郑纬民[1] JI Yu;ZHANG Youhui;ZHENG Weimin(Beijing National Research Center for Information Science and Technology,Department of Computer Science and Technology,Tsinghua University,Beijing 100084,China)

机构地区：[1]清华大学计算机科学与技术系,北京信息科学与技术国家研究中心,北京100084

出　　处：《清华大学学报（自然科学版）》2021年第6期610-617,共8页Journal of Tsinghua University(Science and Technology)

基　　金：北京智源人工智能研究院的资助。

摘　　要：忆阻器是一种非易失性存储器件,目前主要有两种方法用忆阻器实现通用计算:通过忆阻器交叉开关阵列支持神经网络来逼近任意函数;用忆阻器构造基础的门电路,再进一步实现任意Boole逻辑计算。前者存在误差难以控制的问题,后者相比传统数字电路优势不显著。该文设计了一种针对忆阻器的通用近似计算范式,基于忆阻器的硬件架构通用现场可编程突触阵列(GP-FPSA),结合了两种方法的优点来实现基于忆阻器的高效且误差可控的通用近似计算。在具体设计上,充分考虑了神经网络近似能力的限制,通过万能近似器来解决直接训练神经网络误差过大且不可控的问题,并结合控制流实现了复杂函数的拆分,降低近似构造的开销,最后通过基于忆阻器的架构设计,使得通用计算能力大幅提升。Memristors are non-volatile memory devices that are also capable of colocation computations.General-purpose computations can use memristors to approximate arbitrary functions with neural networks or can use memristors to model basic gate circuits that then perform arbitrary Boolean logic calculations.However,the use of memristors to approximate arbitrary functions does not have controllable errors and the use of memristors to model basic gate circuits is slower than conventional digital circuits.This paper presents a general-purpose approximate computing paradigm for memristors and a memristor based hardware architecture,general-purpose field programmable synapse array(GP-FPSA),that combines the advantages of these two methods for efficient general-purpose approximate computing with controllable errors.A universal approximating construction method is used to resolve the large,uncontrollable error of directly training a neural network for approximations.Then,the model control flow splits complicated functions to reduce the construction cost.The memristor-based architecture significantly improves the computational power for general-purpose computing.

关 键 词：近似计算 神经网络 万能近似器 忆阻器 

分 类 号：O242.2[理学—计算数学]